Table 3: Simulation study results based on 500 simulated trials. Sample size and treatment effects as specified in Table 2. Statistical properties of the 2-subgroup direct assignment option design with 1 IA (DAD-1) versus a 2-subgroup balanced randomized design with 1 interim analysis (BRD-1). One-sided and for the subgroup main effects; two-sided for the post-hoc test for an interaction effect.
(a)

Separate subgroup main effects
CaseM+ subgroupM− subgroup
PowerType I error ratePowerType I error rate
DAD-1BRD-1DAD-1BRD-1DAD-1BRD-1DAD-1BRD-1

I (no interaction)78.478.823.820.679.881.820.818.6
II (interaction)78.478.823.820.682.884.419.018.2

(b)

Subgroup-treatment interaction effect
CasePowerType I error rate
DAD-1BRD-1DAD-1BRD-1

I (no interaction)11.311.4
II (interaction)64.367.6